0% found this document useful (0 votes)
6 views5 pages

Quantitative Methods

The document outlines two assignments involving quantitative methods, focusing on hypothesis testing and customer behavior analysis. It details the use of Z tests for proportions and the importance of marginal, joint, and conditional probabilities in understanding customer behavior. The conclusions emphasize the significance of statistical results and the need for targeted marketing strategies based on customer data.

Uploaded by

arakan420gaming
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
6 views5 pages

Quantitative Methods

The document outlines two assignments involving quantitative methods, focusing on hypothesis testing and customer behavior analysis. It details the use of Z tests for proportions and the importance of marginal, joint, and conditional probabilities in understanding customer behavior. The conclusions emphasize the significance of statistical results and the need for targeted marketing strategies based on customer data.

Uploaded by

arakan420gaming
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Quantitative Methods

Assignment – 1
Q1:
Understanding and Usage of Formula:
To test whether the new proportion is significantly different, we use the Z test for proportion.

Formula for Standard Error:


𝑝(1 − 𝑝)
𝑆𝐸 = √
𝑛

Formula for Z-score:


𝑝̂ − 𝑝
𝑧=
𝑆𝐸

 p = population proportion = 0.30


 p̂ = sample proportion = 0.40
 n = sample size = 100

Procedure:
Step 1 – Hypothesis
𝐻0 : P = 0.30

𝐻1 : P ≠ 0.30

Step 2 – Sample Values


n = 100

𝑃̂ = 40/100 = 0.40

P = 0.30

Step 3 – Calculate Standard Error


SE = √[(0.30 × 0.70) / 100]
SE = √(0.21 / 100)
SE = √0.0021 ≈ 0.0458

Step 4 – Calculate Z Value


z = (0.40 − 0.30) / 0.0458
z ≈ 2.18
Step 5 – Critical value
At 5% significance level (two-tailed):
Z critical = ±1.96

Correct Answer & Interpretation


|2.18| > 1.96, we reject the null hypothesis.

Conclusion: The increase from 30% to 40% is statistically significant.

This means the change in student preference is real. The university can consider increasing
Chinese food options.

Q2 (A)
INTRO
In this case, the retail chain is trying to understand customer behaviour using probabilities
from a contingency table. The main problem is whether simple probabilities are enough, or
some deeper analysis like conditional probability is also needed. Also, they need to decide
that gender and purchase frequency are related or independent. This directly affects how
accurately they can target customers.

BODY
Marginal Probability
Marginal probability looks at one variable like:

 Probability of Male customers

 Probability of a customer making frequent purchases

Advantages:
 Simple and easy to calculate

 Gives overall distribution of customers

 Useful for general planning

Disadvantages:
 Ignores relationships between variables
 Not useful for targeted marketing
Note: Marginal probability is good for overview, but not for segmentation.

Joint Probability
Joint probability looks at the combined occurrence of two events, like:

 Probability of a male customer making frequent purchases

Advantages:
 Shows interaction between variables

 Helps identify key customer segments

Disadvantages:
 Still limited in explaining causes

 Harder to Consider for decision-making


Useful for identifying segments, but not enough for Accurate targeting.

Conditional Probability
Conditional probability shows the probability of one event given another, like:

 Probability of frequent purchases given the customer is female

Advantages:
 Most useful for targeted marketing
 Helps understand behaviour within specific groups

 Improves accuracy and personalization

Disadvantages:
 Slightly complex to calculate and interpret

 Requires accurate data

Best tool for segmentation and campaign decisions.

Dependence vs Independence

 If dependent, gender influences purchases → targeted campaigns

 If independent, gender doesn’t affect buying behaviour → generic campaigns


In real life, customer behaviour is rarely independent. There are usually patterns. So,
assuming independence can lead to wrong decision making.

CONCLUSION
Marginal and joint probabilities are useful for basic understanding, but not enough for
targeting. Conditional probability gives the real output needed.

The company should treat gender and purchasing behaviour as dependent and use conditional
probability. This will improve targeting, save budget, and make campaigns more effective.

Q2 (B)
Understanding & Usage of formula
We use the Z score formula for normal distribution:

Z = (X − μ) / σ

X = 180,000
μ = 150,000
σ = 20,000

Procedure
Step 1 – Calculate Z Score
Z = (180,000 − 150,000) / 20,000
Z = 30,000 / 20,000
Z = 1.5

Step 2 – Find Probability


From standard normal table:
P (Z < 1.5) = 0.9332

We need:
P (X > 180,000) = P (Z > 1.5)

So,
P (Z > 1.5) = 1 − 0.9332 = 0.0668
Correct Answer & Interpretation
Final Probability = 0.0668 (6.68%)
This means only about 6.68% of stores earn more than $180,000 per month.
Out of 250 stores, this is approximately 17 stores.

Managerial Interpretation:
 Very few stores reach this level of sales

 Premium category includes only top performers

Conclusion:
The premium threshold appears too strict, since less than 10% of stores qualify.
Management should consider for revising the target or focusing on improving selected stores.

You might also like